TY - GEN
T1 - A self-organizing map with expanding force for data clustering and visualization
AU - SHUM, Wing Ho
AU - JIN, Hui Dong
AU - LEUNG, Kwong Sak
AU - WONG, Man Leung
PY - 2002/1/1
Y1 - 2002/1/1
N2 - The Self-Organizing Map (SOM) is a powerful tool in the exploratory phase of data mining. However, due to the dimensional conflict, the neighborhood preservation cannot always lead to perfect topology preservation. In this paper, we establish an Expanding SOM (ESOM) to detect and preserve better topology correspondence between the two spaces. Our experiment results demonstrate that the ESOM constructs better mappings than the classic SOM in terms of both the topological and the quantization errors. Furthermore, clustering results generated by the ESOM are more accurate than those by the SOM.
AB - The Self-Organizing Map (SOM) is a powerful tool in the exploratory phase of data mining. However, due to the dimensional conflict, the neighborhood preservation cannot always lead to perfect topology preservation. In this paper, we establish an Expanding SOM (ESOM) to detect and preserve better topology correspondence between the two spaces. Our experiment results demonstrate that the ESOM constructs better mappings than the classic SOM in terms of both the topological and the quantization errors. Furthermore, clustering results generated by the ESOM are more accurate than those by the SOM.
UR - http://commons.ln.edu.hk/sw_master/6839
UR - http://www.scopus.com/inward/record.url?scp=8644267845&partnerID=8YFLogxK
U2 - 10.1109/ICDM.2002.1183939
DO - 10.1109/ICDM.2002.1183939
M3 - Conference paper (refereed)
SN - 9780769517544
SP - 434
EP - 441
BT - Proceedings - IEEE International Conference on Data Mining, ICDM
ER -